Export Citations
5 Results for: Author: Cui, Xiaodong
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
Searched The ACM Full-Text Collection (691,749 records)|Expand your search to The ACM Guide to Computing Literature (3,482,418 records)
Showing 1 - 5of5 Results
Select All
- research-articleOctober 2021
Asynchronous Decentralized Distributed Training of Acoustic Models
- Xiaodong Cui,
- Wei Zhang,
- Abdullah Kayi,
- Mingrui Liu,
- Ulrich Finkler,
- Brian Kingsbury,
- George Saon,
- David Kung
IEEE/ACM Transactions on Audio, Speech and Language Processing (TASLP), Volume 292021, pp 3565–3576https://doi.org/10.1109/TASLP.2021.3122349Large-scale distributed training of deep acoustic models plays an important role in today’s high-performance automatic speech recognition (ASR). In this paper we investigate a variety of asynchronous decentralized distributed training strategies ...
- research-articleAugust 2020
Map Generation from Large Scale Incomplete and Inaccurate Data Labels
KDD '20: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data MiningAugust 2020, pp 2514–2522https://doi.org/10.1145/3394486.3403301Accurately and globally mapping human infrastructure is an important and challenging task with applications in routing, regulation compliance monitoring, and natural disaster response management etc.. In this paper we present progress in developing an ...
- research-articleMarch 2018
MeTDiff: A Novel Differential RNA Methylation Analysis for MeRIP-Seq Data
IEEE/ACM Transactions on Computational Biology and Bioinformatics (TCBB), Volume 15, Issue 2March 2018, pp 526–534https://doi.org/10.1109/TCBB.2015.2403355N6-Methyladenosine m6A transcriptome methylation is an exciting new research area that just captures the attention of research community. We present in this paper, MeTDiff, a novel computational tool for predicting differential m6A methylation sites ...
- research-articleNovember 2016
Maximum Likelihood Nonlinear Transformations Based on Deep Neural Networks
IEEE/ACM Transactions on Audio, Speech and Language Processing (TASLP) (TASLP), Volume 24, Issue 11November 2016, pp 2023–2031https://doi.org/10.1109/TASLP.2016.2594255Feature transformations are commonly used in speech recognition to account for distribution mismatches between the source and target domains also referred to as covariate shift. Linear affine or piecewise linear transformations are typically considered. ...
- research-articleSeptember 2015
Data augmentation for deep neural network acoustic modeling
IEEE/ACM Transactions on Audio, Speech and Language Processing (TASLP) (TASLP), Volume 23, Issue 9September 2015, pp 1469–1477https://doi.org/10.1109/TASLP.2015.2438544This paper investigates data augmentation for deep neural network acoustic modeling based on label-preserving transformations to deal with data sparsity. Two data augmentation approaches, vocal tract length perturbation (VTLP) and stochastic feature ...
